lasith-tekly/ai-plc
Open-source agent harness for product ideation and planning. PM-led, with human approval at every stop. Hands over to Scrum or AI-DLC.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
up to ~20.7k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http notion https://mcp.notion.com/mcp $ claude mcp add --transport http atlassian https://mcp.atlassian.com/v2/mcp $ claude mcp add --transport http miro https://mcp.miro.com/ $ npx degit lasith-tekly/ai-plc/agents ./rig-ai-plc/agents $ npx degit lasith-tekly/ai-plc/commands ./rig-ai-plc/commands $ npx degit lasith-tekly/ai-plc/skills ./rig-ai-plc/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add --transport http notion https://mcp.notion.com/mcp $ claude mcp add --transport http atlassian https://mcp.atlassian.com/v2/mcp $ claude mcp add --transport http miro https://mcp.miro.com/
$ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-connectors .claude/skills/ai-plc-connectors $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-delivery-ai-dlc .claude/skills/ai-plc-delivery-ai-dlc $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-delivery-plain .claude/skills/ai-plc-delivery-plain $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-delivery-scrum .claude/skills/ai-plc-delivery-scrum $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-gate-pack .claude/skills/ai-plc-gate-pack $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-idea-intake .claude/skills/ai-plc-idea-intake $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-market-and-customers .claude/skills/ai-plc-market-and-customers $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-outcome-pack .claude/skills/ai-plc-outcome-pack $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-review .claude/skills/ai-plc-review $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-solution .claude/skills/ai-plc-solution $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-strategy .claude/skills/ai-plc-strategy $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc-viability .claude/skills/ai-plc-viability $ npx degit lasith-tekly/ai-plc/plugins/ai-plc/skills/ai-plc .claude/skills/ai-plc $ npx degit lasith-tekly/ai-plc/powers/ai-plc/skills/ai-plc-setup .claude/skills/ai-plc-setup $ npx degit lasith-tekly/ai-plc/skills/connectors .claude/skills/connectors $ npx degit lasith-tekly/ai-plc/skills/delivery-ai-dlc .claude/skills/delivery-ai-dlc $ npx degit lasith-tekly/ai-plc/skills/delivery-plain .claude/skills/delivery-plain $ npx degit lasith-tekly/ai-plc/skills/delivery-scrum .claude/skills/delivery-scrum $ npx degit lasith-tekly/ai-plc/skills/gate-pack .claude/skills/gate-pack $ npx degit lasith-tekly/ai-plc/skills/idea-intake .claude/skills/idea-intake $ npx degit lasith-tekly/ai-plc/skills/market-and-customers .claude/skills/market-and-customers $ npx degit lasith-tekly/ai-plc/skills/outcome-pack .claude/skills/outcome-pack $ npx degit lasith-tekly/ai-plc/skills/review .claude/skills/review $ npx degit lasith-tekly/ai-plc/skills/solution .claude/skills/solution $ npx degit lasith-tekly/ai-plc/skills/strategy .claude/skills/strategy $ npx degit lasith-tekly/ai-plc/skills/viability .claude/skills/viability
$ curl -fsSL --create-dirs -o .claude/agents/delivery.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/delivery.md $ curl -fsSL --create-dirs -o .claude/agents/discovery.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/discovery.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/outcome.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/outcome.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/solution.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/solution.md $ curl -fsSL --create-dirs -o .claude/agents/strategy.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/strategy.md $ curl -fsSL --create-dirs -o .claude/agents/viability.md https://raw.githubusercontent.com/lasith-tekly/ai-plc/main/agents/viability.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (3)
| server | source | est. tokens |
|---|---|---|
| Notion | remote · remote | 6.0k |
| Atlassian | remote · remote | 10.0k |
| mcp.miro.com · "miro" | remote · remote | 2.5k |
Skills (26)
ai-plc-connectorsai-plc-delivery-ai-dlcai-plc-delivery-plainai-plc-delivery-scrumai-plc-gate-packai-plc-idea-intakeai-plc-market-and-customersai-plc-outcome-packai-plc-reviewai-plc-solutionai-plc-strategyai-plc-viabilityai-plcai-plc-setupconnectorsdelivery-ai-dlcdelivery-plaindelivery-scrumgate-packidea-intakemarket-and-customersoutcome-packreviewsolutionstrategyviability
Subagents (8)
| ai-plc-delivery | Delivery agent for AI-PLC --full runs. After the Outcome Pack is issued, produces requirements, epics, user stories and their dependency maps (Scrum), AI-DLC handoff briefs, or a plain outcome list. U |
| ai-plc-discovery | Phase 1 agent for AI-PLC. Drafts the problem and opportunity statement, market definition, customer definition and existing research summary. Used by the orchestrator. |
| ai-plc-orchestrator | Entry point for AI-PLC. Reads the run mode, plans the run, assigns work to the specialist agents, tracks status and manages every review stop, checkpoint and gate. Use when the PM runs /ai-plc. |
| ai-plc-outcome | Outcome Definition agent for AI-PLC. After Gate 2 is approved, turns the approved evidence into an Outcome Pack: one file per outcome plus an index. Used by the orchestrator. |
| ai-plc-reviewer | Independent review agent for AI-PLC. Checks approved deliverables before a checkpoint or gate for unsupported claims, broken sources, inconsistencies and scope breaches. Reports findings only. Used by |
| ai-plc-solution | Phase 3 agent for AI-PLC. Drafts prioritised capabilities, solution research and design, usability test plan, positioning and messaging, pilot plan and MVP scope. Used by the orchestrator. |
| ai-plc-strategy | Phase 2 agent for AI-PLC. Drafts use cases, outcome-oriented scope, strategy considerations, pricing check, business model canvas, vision statement and the initial business case. Used by the orchestra |
| ai-plc-viability | Phase 4 agent for AI-PLC. Drafts the legal and security assessment template, risk assessment, implementability, product and market viability, measurement plan, value assessment, pricing strategy, serv |
Slash commands (1)
/ai-plc
Similar rigs
demian-v/claude-qa-mcp
A ready-to-use Claude Code MCP server starter for QA engineers: Miro, Atlassian (Jira/Confluence), TestRail, and Playwright in one config. Figma setup walkthrough included in the README.
Pragmatist 22.5k tok · · Q0
JaKXz/.zsh-custom
—
Pragmatist 26.2k tok · · Q15
pwntester/dotfiles
—
Skill Collector 14.5k tok · · Q0
sora-ichigo/dotfiles
—
YOLO Cowboy 40.6k tok · · Q8